Import an existing wallet from a private key
AI agents use import-wallet to create or update resources in MCP EVM Signer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP EVM Signer environment.
This tool writes/creates a new wallet entry in the MCP server's wallet management system. While it doesn't directly move funds (preventing Financial classification), importing a wallet gives the system persistent access to manage that private key, making it a high-severity Write operation.
From the tool's definition Tool imports an existing wallet from a private key, creating or adding a wallet entry to the local key management system. Description indicates 'Import an existing wallet', which creates a new managed wallet record.
Attacks that exploit this kind of access
Import an existing wallet from a private key. It is categorised as a Write tool in the MCP EVM Signer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP EVM Signer MCP server in PolicyLayer and add a rule for import-wallet: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP EVM Signer. Nothing to install.
import-wallet is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the import-wallet rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for import-wallet. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
import-wallet is provided by the MCP EVM Signer MCP server (zhangzhongnan928/mcp-evm-signer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →